While large language models (LLMs) have demonstrated impressive performance in question-answering tasks, their performance is limited when the questions require knowledge that is not included in the model's training data and can only be acquired through direct observation or interaction with the real world. Existing methods decompose reasoning tasks through the use of modules invoked sequentially, limiting their ability to answer deep reasoning tasks. We introduce a method, Recursion based extensible LLM (REBEL), which handles open-world, deep reasoning tasks by employing automated reasoning techniques like dynamic planning and forward-chaining strategies. REBEL allows LLMs to reason via recursive problem decomposition and utilization of external tools. The tools that REBEL uses are specified only by natural language description. We further demonstrate REBEL capabilities on a set of problems that require a deeply nested use of external tools in a compositional and conversational setting.

翻译：虽然大型语言模型（LLMs）在问答任务中展现了出色性能，但当问题要求获取模型训练数据中未包含、仅通过直接观察或与现实世界交互才能获得的知识时，其性能会受到限制。现有方法通过顺序调用模块来分解推理任务，这限制了其回答深度推理任务的能力。我们提出了一种基于递归的可扩展LLM方法（REBEL），该方法通过采用动态规划和前向链策略等自动推理技术来处理开放世界中的深度推理任务。REBEL通过递归问题分解和外部工具利用来驱动LLM进行推理，其使用的工具仅通过自然语言描述来指定。我们进一步在需要多嵌套使用外部工具的组合式对话问题集上展示了REBEL的能力。